© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118811
    Prev
    Next
    INDEX
    Explanations

    object, entity, reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dummies
    -0.06
     absorbent
    -0.06
    absorbed
    -0.06
     nltk
    -0.06
    接觸
    -0.06
     yogurt
    -0.06
     Yolanda
    -0.06
     unserer
    -0.06
    alia
    -0.06
     spille
    -0.06
    POSITIVE LOGITS
     ಆಧ
    0.07
    文明
    0.06
     என்ன
    0.06
    队列
    0.06
     spesso
    0.05
    ariamente
    0.05
     ಸಂತ
    0.05
     often
    0.05
     मोटर
    0.05
     yür
    0.05
    Activations Density 0.001%

    No Known Activations